1.5k citations · 1.8k across the 13 of their papers we have counts for
14 papers
Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior
Christopher J. Anders, Henrique Da Silva Gameiro, Nico Daheim +1
One way to understand LLM behavior is to trace its output back to the training data. Two types of measures are commonly used for output tracing: data-similarity and data-influence.…
Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation
Sidney Bender, Christopher J. Anders, Pattarawatt Chormai +3
This paper introduces a novel technique called counterfactual knowledge distillation (CFKD) to detect and remove reliance on confounders in deep learning models with the help of hu…
From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space
Maximilian Dreyer, Frederik Pahde, Christopher J. Anders +2
Deep Neural Networks are prone to learning spurious correlations embedded in the training data, leading to potentially biased predictions. This poses risks when deploying these mod…
Detecting and Mitigating Mode-Collapse for Flow-based Sampling of Lattice Field Theories
Kim A. Nicoli, Christopher J. Anders, Tobias Hartung +3
We study the consequences of mode-collapse of normalizing flows in the context of lattice field theory. Normalizing flows allow for independent sampling. For this reason, it is hop…
Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
Frederik Pahde, Maximilian Dreyer, Leander Weber +5
With a growing interest in understanding neural network prediction strategies, Concept Activation Vectors (CAVs) have emerged as a popular tool for modeling human-understandable co…
Machine Learning of Thermodynamic Observables in the Presence of Mode Collapse
Kim A. Nicoli, Christopher Anders, Lena Funcke +5
Estimating the free energy, as well as other thermodynamic observables, is a key task in lattice field theories. Recently, it has been pointed out that deep generative models can b…